Triple
T3455685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATMB |
E72897
|
entity |
| Predicate | operates |
P24
|
FINISHED |
| Object | Mont Blanc Tunnel |
E15106
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mont Blanc Tunnel | Statement: [ATMB, operates, Mont Blanc Tunnel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont Blanc Tunnel Context triple: [ATMB, operates, Mont Blanc Tunnel]
-
A.
Mont Blanc Tunnel
chosen
The Mont Blanc Tunnel is a major trans-Alpine road tunnel linking France and Italy beneath the Mont Blanc massif, serving as a key route for international traffic through the Alps.
-
B.
Fréjus Road Tunnel
The Fréjus Road Tunnel is a major trans-Alpine highway tunnel linking France and Italy through the Alps, serving as an important route for international road traffic.
-
C.
Fréjus Rail Tunnel
The Fréjus Rail Tunnel is a major Alpine railway tunnel linking France and Italy, playing a key role in trans-European rail transport.
-
D.
Vielha Tunnel
Vielha Tunnel is a major road tunnel in the central Pyrenees that provides a key transport link connecting the Val d’Aran with the rest of Catalonia and Spain.
-
E.
Léman Pass
Léman Pass is a regional fare system that allows integrated ticketing and seamless travel across multiple public transport networks in the Greater Geneva area and surrounding cross-border regions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa77b9c81909376a5995cdaf6ac |
completed | March 8, 2026, 6:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b361014b1c81909b6db97ec2395b73 |
completed | March 13, 2026, 12:57 a.m. |
Created at: March 8, 2026, 3:16 p.m.